STABLE FLIGHT CONTROL METHOD FOR MULTI-ROTOR UNMANNED AERIAL VEHICLE BASED ON FINITE-TIME NEURODYNAMICS

摘要

A stable flight control method for a multi-rotor unmanned aerial vehicle based on finite-time neurodynamics, comprising the following implementation process: 1) acquiring real-time flight orientation and attitude data by airborne sensors, analyzing and solving a kinematics problem of an aerial vehicle by an airborne processor, and establishing a dynamics model of the aerial vehicle; 2) designing a finite-time variable parameter convergence differential neural network solver according to a finite-time variable parameter convergence differential neurodynamics design method; 3) solving an output control amount of each motor of the aerial vehicle by the finite-time variable parameter convergence differential neural network solver using the acquired real-time orientation and attitude data; and 4) transmitting the solution result to each motor speed regulator of the aerial vehicle to control the unmanned aerial vehicle to move. By means of the method based on finite-time variable parameter convergence differential neurodynamics, a correct solution can be approximated in quick, accurate, and real-time fashion, and many time dependent problems such as matrix, vector, algebra, and optimization can be well solved.